{"as_of":"2026-08-12T05:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5df8b37dd577eed284a26e4046be0f6e208608865e413306538083dbe6e5a019","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T18:11:54.511203Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-10T15:56:38.088828Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.11732","last_updated":"2023-06-15T20:56:20Z","snapshot_observed_at":"2026-08-09T18:50:50.538190Z","submitted_at":"2023-06-15T20:56:20Z","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11732","snapshot_observed_at":"2026-08-11T18:11:54.511203Z","title":"Retrieving-to-answer: Zero-shot video question answering with frozen large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08158","last_updated":"2024-12-11T07:29:04Z","snapshot_observed_at":"2026-08-11T20:29:00.311316Z","submitted_at":"2024-12-11T07:29:04Z","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T18:11:54.511203Z"},"links":{"cited_paper":"/paper/2306.11732","citing_paper":"/paper/2412.08158"},"observation_digest":"sha256:1e3b00ba74b0567e40faa14c76ef1af8f64ef0d70391108c12f3340154ea7ff1","observation_id":"a32b45dd-6a49-4ecb-8d6a-4a7ac9906df4","resolution":{"observed_at":"2026-08-11T18:11:54.511203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11732","last_updated":"2023-06-15T20:56:20Z","snapshot_observed_at":"2026-08-09T18:50:50.538190Z","submitted_at":"2023-06-15T20:56:20Z","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","version":1},"cited_work":{"arxiv_id":"2306.11732","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.11732","snapshot_observed_at":"2026-08-10T15:56:38.088828Z","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","venue":"cs.CV","work_id":"a682654a-5587-42cb-8ee1-7e1b9984c4be","year":2023},"citing_paper":{"arxiv_id":"2501.13536","last_updated":"2025-01-23T10:35:22Z","snapshot_observed_at":"2026-08-11T18:26:40.310791Z","submitted_at":"2025-01-23T10:35:22Z","title":"ReasVQA: Advancing VideoQA with Imperfect Reasoning Process","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T15:56:37.604004Z"},"links":{"cited_paper":"/paper/2306.11732","citing_paper":"/paper/2501.13536"},"observation_digest":"sha256:17ce446517639dd9e2d3e9f6a0f400d6a02e35a9349a731bd0364f6b683be702","observation_id":"1a4b43cc-d494-446c-8fb1-b75fa54fcc52","resolution":{"observed_at":"2026-08-10T15:56:38.093073Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2306.11732/citation-record","integrity":"/paper/2306.11732/integrity","json":"/paper/2306.11732/citation-record.json","paper":"/paper/2306.11732"},"outbound":[],"paper":{"arxiv_id":"2306.11732","last_updated":"2023-06-15T20:56:20Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T18:50:50.538190Z","submitted_at":"2023-06-15T20:56:20Z","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2306.11732."}